Learning Discriminative Virtual Sequences for Time Series Classification
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Temporal data are continuously collected in a wide range of domains. The increasing availability of such data has led to significant developments of time series analysis. Time series classification, as an essential task in time series analysis, aims to assign a set of temporal sequences to different categories. Among various approaches for time series classification, the distance metric learning based ones, such as the virtual sequence metric learning (VSML), have attracted increased attention due to their remarkable performance. In VSML, virtual sequences attract samples from different classes to facilitate time series classification. However, the existing VSML methods simply employ fixed virtual sequences, which might not be optimal for the subsequent classification tasks. To address this issue, in this paper, we propose a novel time series classification method named Discriminative Virtual Sequence Learning (DVSL). Following the unified framework of sequence metric learning, our DVSL method jointly learns a set of discriminative virtual sequences that help separate time series samples in a feature space, and optimizes the temporal alignment by dynamic time warping. Extensive experiments on 15 UCR time series datasets demonstrate the efficiency of DVSL, compared with several representative baselines.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“TapNet [137] and DVSL [138] are explicit prototypes contrast because explicit prototypes are introduced.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [138]
In the citing paper
“DVSL defines virtual sequences, which have the same function as prototypes, i.e., minimize the distance between samples and virtual sequences, but maximize the distance between virtual sequences.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [138]
Citations
Cites
(1994) · Knowledge Discovery and Data Mining · Cited by 3,137
Time series classification from scratch with deep neural networks: A strong baseline
Wang, Z., Yan, W., & Oates, T. (2017) · 2017 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966039 · Cited by 2,299 · cited 1×
“The deep learning methods have obtained remarkable performance [5, 14].”
MethodLSTM Fully Convolutional Networks for Time Series Classification
Karim, F., Majumdar, S., Darabi, H., & Chen, S. (2018) · IEEE Access · doi:10.1109/access.2017.2779939 · Cited by 1,465 · cited 1×
“The deep learning methods have obtained remarkable performance [5, 14].”
MethodTime series shapelets: a new primitive for data mining
Ye, L., & Keogh, E. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557122 · Cited by 987 · cited 1×
“Local feature based methods extract representative attributes from time series, such as the shapelets, which are defined as time series subsequences that maximally represent a class [12, 15].”
MethodZheng, Y., Liu, Q., Chen, E., Ge, Y., & Zhao, J. L. (2016) · Frontiers of Computer Science · doi:10.1007/s11704-015-4478-2 · Cited by 273 · cited 1×
“For instance, a deep learning architecture based on multi-channel deep convolutional neural networks is proposed to classify multivariate time series data [18].”
BackgroundFeature-based classification of time-series data
Νανόπουλος, Α., Alcock, R. J., & Manolopoulos, Y. (2001) · Cited by 259
Temporal Subspace Clustering for Human Motion Segmentation
Li, S., Li, K., & Fu, Y. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.506 · Cited by 108 · cited 1×
“Some fundamental time series analysis tasks include classification, prediction, anomaly detection, clustering and visualization [7–9].”
BackgroundSelf-citationLearning DTW-Shapelets for Time-Series Classification
Shah, M., Grabocka, J., Schilling, N., Wistuba, M., & Schmidt-Thieme, L. (2016) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/2888451.2888456 · Cited by 54 · cited 1×
“Local feature based methods extract representative attributes from time series, such as the shapelets, which are defined as time series subsequences that maximally represent a class [12, 15].”
MethodMulti-View Time Series Classification
Li, S., Li, Y., & Fu, Y. (2016) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2983323.2983780 · Cited by 47 · cited 2×
“Some fundamental time series analysis tasks include classification, prediction, anomaly detection, clustering and visualization [7–9].”
BackgroundMethodSelf-citationRegressive Virtual Metric Learning
Perrot, M., & Habrard, A. (2015) · HAL · Cited by 37
Locally Slope-based Dynamic Time Warping for Time Series Classification
Yuan, J., Lin, Q., Zhang, W., & Wang, Z. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357917 · Cited by 33
A large margin time series nearest neighbour classification under locally weighted time warps
Yuan, J., Douzal-Chouakria, A., Yazdi, S. V., & Wang, Z. (2018) · Knowledge and Information Systems · doi:10.1007/s10115-018-1184-z · Cited by 28 · cited 2×
“Many variants of DTW have been proposed to improve the performance and reduce the time complexity [16, 17].”
BackgroundMethodEarly Recognition of 3D Human Actions
Li, S., Li, K., & Fu, Y. (2018) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3131344 · Cited by 23
Self-citationEarly Classification of Ongoing Observation
Li, K., Li, S., & Fu, Y. (2014) · Proceedings · doi:10.1109/icdm.2014.100 · Cited by 22 · cited 1×
“A lot of methods have been proposed for time series classification [6, 9], including the local feature based methods [10], deep learning based methods [4], and metric learning based meth-ods [1, 13].”
MethodSelf-citationDeep Prototypical Networks for Imbalanced Time Series Classification under Data Scarcity
Huang, C., Wu, X., Zhang, X., Lin, S., & Chawla, N. V. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358162 · Cited by 18 · cited 4×
“Deep learning based methods learn a latent feature space for time series data, which have obtained impressive performance [3, 4].”
BackgroundMethodInfluentialProbability Model-Based Early Merge Mode Decision for Dependent Views Coding in 3D-HEVC
Li, Y., Yang, G., Zhu, Y., Ding, X., & Gong, R. (2018) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3267128 · Cited by 15
Natural Timestamps in Powerline Electromagnetic Radiation
Li, Y., Tan, R., & Yau, D. K. Y. (2018) · ACM Transactions on Sensor Networks · doi:10.1145/3199676 · Cited by 12
Hashida, S., & Tamura, K. (2019) · IEEE International Workshop on Computational Intelligence and Applications (IWCIA) · doi:10.1109/iwcia47330.2019.8955030 · Cited by 10 · cited 2×
“Deep learning based methods learn a latent feature space for time series data, which have obtained impressive performance [3, 4].”
MethodLearning distance for sequences by learning a ground metric
Su, B., & Wu, Y. N. (2019) · International Conference on Machine Learning · Cited by 7
Cited by
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“TapNet [137] and DVSL [138] are explicit prototypes contrast because explicit prototypes are introduced.”
BackgroundTARNet: Task-Aware Reconstruction for Time-Series Transformer
Chowdhury, R. R., Zhang, X., Shang, J., Gupta, R. K., & Hong, D. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539329 · Cited by 68
“Distance-based methods [8, 31] use distance metric to measure similarity of a pair of time series.”
MethodSMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Series
Zuo, J., Zeitouni, K., & Taher, Y. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00206 · Cited by 25
Correlative Channel-Aware Fusion for Multi-View Time Series Classification
Bai, Y., Wang, L., Tao, Z., Li, S., & Fu, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16830 · Cited by 28
“Other distance based models are also proposed for TSC such as (Wei and Keogh 2006; Dorle et al. 2020; Ratanamahatana and Keogh 2004; Keogh and Kasetty 2003).”
BackgroundSelf-citationSoft Subspace Based Ensemble Clustering for Multivariate Time Series Data
He, G., Jiang, W., Peng, R., Yin, M., & Han, M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3146136 · Cited by 19
“Moreover, Dorle et al. [24] grouped time series samples in feature space by learning a set of discriminative virtual sequences.”
Background
Metadata
- Authors
- Dorle, A., Li, F., Song, W., & Li, S.
- Affiliations
- University of Georgia (US)
- Kennesaw State University (US)
- University of Georgia, Athens, GA, USA
- ORCID
- Venue
- Proceedings of the 29th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2020-10-19
- Pages
- 2001-2004
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W3093525187
- Cited by
- 11
- References
- 19
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 1 · 2022: 2 · 2021: 5
- FWCI
- 1.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- time series classification, metric learning, dynamic time warping, temporal alignment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.